commit b136eaf79615d98db920573cf096e13556515dd1 Author: ModelHub XC Date: Tue Oct 6 20:08:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-14B-Chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..58d54fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-14B-Chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-14B-Chat.i1-IQ1_M.gguf b/Qwen1.5-14B-Chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..db4fd83 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18b8e798d8654ca066ef66798ec527064622ba8bcf26b6606ef4f1aa35b2788 +size 4678902496 diff --git a/Qwen1.5-14B-Chat.i1-IQ1_S.gguf b/Qwen1.5-14B-Chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..1bd7486 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c2de676acef6757dbc86bab3a8bcf0792cf5d51c54f5f89718cb9227d6a9c8 +size 4498268896 diff --git a/Qwen1.5-14B-Chat.i1-IQ2_M.gguf b/Qwen1.5-14B-Chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..8f52e9e --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e82b8dffb02a5ce336a81ae445d673a9c91efb45c14d45793c4ec4da3119380 +size 5827441376 diff --git a/Qwen1.5-14B-Chat.i1-IQ2_S.gguf b/Qwen1.5-14B-Chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..673a3d6 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49db181b9e1d7270e3ed7786e7643b8fc941225915de2cb01b3af067f41f6fee +size 5586596576 diff --git a/Qwen1.5-14B-Chat.i1-IQ2_XS.gguf b/Qwen1.5-14B-Chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5936198 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f044345f801f2b235d529e9c283a2c60e8d2c17bc8408795b785863fc22f837 +size 5253571296 diff --git a/Qwen1.5-14B-Chat.i1-IQ2_XXS.gguf b/Qwen1.5-14B-Chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..93ae163 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e3d6c7351b085b1a2310e553c799158b586d64703d2f5cd6e29f72c69c1593 +size 4979958496 diff --git a/Qwen1.5-14B-Chat.i1-IQ3_M.gguf b/Qwen1.5-14B-Chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..2c70b5e --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7e0a45ff0143e4c04a4b151e90ede1a0744f549acb8459bc0bd5b7837645a4 +size 7096156896 diff --git a/Qwen1.5-14B-Chat.i1-IQ3_S.gguf b/Qwen1.5-14B-Chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..81db04f --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946595407c112bd374c6d4a29e2804677bb4a0f0f3cacb4cf1bb3faae4c2fdfd +size 6773801696 diff --git a/Qwen1.5-14B-Chat.i1-IQ3_XS.gguf b/Qwen1.5-14B-Chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..bb30bc1 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea9fbc638245280e9e35362b785f4dad4dbcd6e2fd89e719e3685768ef7e88f +size 6478275296 diff --git a/Qwen1.5-14B-Chat.i1-IQ3_XXS.gguf b/Qwen1.5-14B-Chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..796b5a1 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49eede04d0092cb66cafa4470a8188421be57eeccd5c68ae0cfc18998f036412 +size 6128906976 diff --git a/Qwen1.5-14B-Chat.i1-IQ4_XS.gguf b/Qwen1.5-14B-Chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..a282df4 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e395230c2547265d678a5a559f3fbfa76acfe5192719ebd8432af808706a5b6 +size 7848612576 diff --git a/Qwen1.5-14B-Chat.i1-Q2_K.gguf b/Qwen1.5-14B-Chat.i1-Q2_K.gguf new file mode 100644 index 0000000..9781514 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85712b797b87ee7bb515034e44f5d04a6fbb3accdbf60fb486b0b619ac3d0340 +size 5911982816 diff --git a/Qwen1.5-14B-Chat.i1-Q3_K_L.gguf b/Qwen1.5-14B-Chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..873dffb --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa7b66a7b917ecf14decf5135977ff27f8ac2a845fc3793c2a4b6b2aa841a79 +size 7840400096 diff --git a/Qwen1.5-14B-Chat.i1-Q3_K_M.gguf b/Qwen1.5-14B-Chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..91f331e --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc011b5e18326b76205881bfc3622eacdbf77060c13108fe0f94b925ae558ce +size 7418266336 diff --git a/Qwen1.5-14B-Chat.i1-Q3_K_S.gguf b/Qwen1.5-14B-Chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a375741 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac7a84f0ba6f6a965de76ab0156fe88498ff836a62a44dbed38c22ab3b21090 +size 6773801696 diff --git a/Qwen1.5-14B-Chat.i1-Q4_0.gguf b/Qwen1.5-14B-Chat.i1-Q4_0.gguf new file mode 100644 index 0000000..754bc95 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f8ecee8856f8387932fc3656ab5e9f4eef1245345ce32a9913413d1a096c6d +size 8201237216 diff --git a/Qwen1.5-14B-Chat.i1-Q4_0_4_4.gguf b/Qwen1.5-14B-Chat.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..ea59b3f --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8676e9fed215767b05b7c211f6206c64df0da9fe079f295e16f83548b341e4 +size 8179323616 diff --git a/Qwen1.5-14B-Chat.i1-Q4_0_4_8.gguf b/Qwen1.5-14B-Chat.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..d16fd7c --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed54ac5c91f538a63005ae23dfdf41f98ef34f0a149ea32aa25008a68adea32 +size 8179323616 diff --git a/Qwen1.5-14B-Chat.i1-Q4_0_8_8.gguf b/Qwen1.5-14B-Chat.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..1de6e18 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490f41ceebdadb0e3764570993293862d5347a6e1b884e911bb6bebc0d487376 +size 8179323616 diff --git a/Qwen1.5-14B-Chat.i1-Q4_K_M.gguf b/Qwen1.5-14B-Chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ee66f3b --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e8933a4b27e9cf0d1258e8ad5b2120454bd2cd5890e20e314140ebf079e3b6 +size 9191035616 diff --git a/Qwen1.5-14B-Chat.i1-Q4_K_S.gguf b/Qwen1.5-14B-Chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..82eec34 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a20e7a117a84f025d54199cfea9301e698a42135c855db26c669981d567294f0 +size 8564962016 diff --git a/Qwen1.5-14B-Chat.i1-Q5_K_M.gguf b/Qwen1.5-14B-Chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4a701bc --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3024d792a9593f8ef3637e9f7ef112894d195ba0a3de3059d2c8793c76dd39a +size 10535998176 diff --git a/Qwen1.5-14B-Chat.i1-Q5_K_S.gguf b/Qwen1.5-14B-Chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e1cb709 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d8a04b8b14dfaf79de3c4e53e4ace5fd687e0f43f745734ddf9c374cce0d96 +size 10028094176 diff --git a/Qwen1.5-14B-Chat.i1-Q6_K.gguf b/Qwen1.5-14B-Chat.i1-Q6_K.gguf new file mode 100644 index 0000000..b53a625 --- /dev/null +++ b/Qwen1.5-14B-Chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed98520b5fb9076360b51b64e420983affdc0e3b406f66ac312341bb21f44b7 +size 12310160096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2c9dd01 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Qwen/Qwen1.5-14B-Chat +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-14B-Chat/blob/main/LICENSE +license_name: tongyi-qianwen +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-14B-Chat + + +static quants are available at https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 4.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 6.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 6.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.3 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.3 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.3 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 8.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-14B-Chat-i1-GGUF/resolve/main/Qwen1.5-14B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..07d357a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662560e37d28a5cdf6d707742e41aadb7ff06c364385af333e8f30d7a186e74c +size 7115845